© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21462
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antiques
    -0.09
    _selected
    -0.08
     Medal
    -0.08
     probably
    -0.08
    (selected
    -0.08
     likely
    -0.08
    콩
    -0.08
     biodiversity
    -0.08
    -selected
    -0.08
     收藏
    -0.08
    POSITIVE LOGITS
     shift
    0.13
     shifting
    0.12
     shifts
    0.11
     Rewrite
    0.11
     delaying
    0.11
     rewriting
    0.11
     Shift
    0.10
     offset
    0.10
     equival
    0.10
    _SHIFT
    0.10
    Activations Density 0.023%

    No Known Activations